Parameter Constrained Neural Network

Model overview

Parameter constrained neural network classifier using PyTorch with configurable hidden layers to predict taxonomy IDs from product tags. Each taxonomy path is encoded as a p-adic integer and the model minimizes p-adic distance.

5 CV folds

15.56% Mean accuracy

0.1094 Mean F1

0.79190526 Mean p-adic loss

Total train samples: 18,320
Total test samples: 4,580

Key hyperparameters

Prime base(s): 79
Hidden layer sizes: 27
Max tags used: 32

Cross-validation results

Fold	Accuracy	F1	P-adic loss (mean)	Details
0	15.72%	0.1150	0.796668	View details →
1	16.79%	0.1208	0.776087	View details →
2	14.60%	0.0984	0.784729	View details →
3	13.83%	0.0933	0.821545	View details →
4	16.87%	0.1196	0.780498	View details →